Related papers: How to Learn a New Language? An Efficient Solution…

Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with…

While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language…

Self-Supervised Learning (SSL) has emerged as the solution of choice to learn transferable representations from unlabeled data. However, SSL requires to build samples that are known to be semantically akin, i.e. positive views. Requiring…

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

Self-supervised pre-trained audio networks have seen widespread adoption in real-world systems, particularly in multi-modal large language models. These networks are often employed in a frozen state, under the assumption that the SSL…

Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning…

Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large training dataset and hard to achieve comparable performance under low-resource conditions. To address this…

Self-supervised learning (SSL) models have become crucial in speech processing, with recent advancements concentrating on developing architectures that capture representations across multiple timescales. The primary goal of these…

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…

Sound source localization (SSL) is essential for many speech-processing applications. Deep learning models have achieved high performance, but often fail when the training and inference environments differ. Adapting SSL models to dynamic…

Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a 'pretext task' that does not require ground-truth labels/annotation. This…

Adapting pre-trained text Large Language Models (LLMs) into Speech Language Models (Speech LMs) via continual pretraining on speech data is promising, but often degrades the original text capabilities. We propose Multimodal Depth Upscaling,…

Code-switching (CS) is common in daily conversations where more than one language is used within a sentence. The difficulties of CS speech recognition lie in alternating languages and the lack of transcribed data. Therefore, this paper uses…

While Automatic Speech Recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to new domains and need to be finetuned on data from these domains. However, target-domain data usually are…

Recent advancements in deep learning have significantly enhanced multilingual automatic speech recognition (ASR) due to the development of advanced model architectures and available large-scale multilingual datasets. Despite that,…

In this paper, we investigate domain adaptation for low-resource Automatic Speech Recognition (ASR) of target-domain data, when a well-trained ASR model trained with a large dataset is available. We argue that in the encoder-decoder…

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such…

Code-switching (CS) phenomenon occurs when words or phrases from different languages are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic Speech Recognition (ASR) system remains challenging. In this…

Large-scale multilingual ASR models like Whisper excel in high-resource settings but face challenges in low-resource scenarios, such as rare languages and code-switching (CS), due to computational costs and catastrophic forgetting. We…

We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind. We discuss SSL for AMs in a small…